endymion-light

I'm sorry but all this proves is that a lot of published stories aren't very good. The three human stories attached don't have fantastic plot and read a little poorly.

All three of the human written stories read like they were made for a reviewer/publisher rather than a reader.

I don't think this is a good study or a good representation of good writing. I think many short stories have the issue of force feeding so much information and tricks that the 3 human stories read more gimmicky than the chatgpt ones.

Then this entire conversation is a pointless argument - as I agree that models aren't omniscient, godlike entities that are perfect sources of truth, and that you need to use critical thinking when using them.

I don't trust models blindly, and interrogate and verify claims that they make, but that's a basic component of being a human being.

I also never try to have massive multi step conversations to the point where I'm nearing the context limits, as if there's a subclaim i need to interrogate it's far better to clear context and just start a new chat, I have notes to join up ideas.

When learning, I'm not just doing so blindly asking a model questions, I have other material up, I can look at the answer to a example question from a textbook to verify whether I have used a model to successfully learn.

This conversation is just going to devolve further into a "well it doesn't always work" to which yes, I agree, but that doesn't mean it's not useful and doesn't help the learning process.

Firstly, I can't refute a point that's little more than an opinion - my doubt is that a modern frontier model is significantly hallucinating within a relatively short conversation that can easily be verified. There is no way to refute or accept the point without a complete conversation log. I am criticizing the hyperbolic nature of the comment.

I doubt you are getting to the context level of model degredation where it reaches context limits within a verbal hour conversation.

I've just tried to recreate your example on sonnet 5, and as someone who has done DIY projects it reads completely appropriate, but I'm happy for criticism from a shed builder. It never once tells me about paper machie or creates a silly example.

This is via a prompt requesting tools and materials, and could be further improved, unfortunately, I can't paste the markdown formatting provided.

""" Reference size used below: 8x10 ft shed. Scale material quantities to your dimensions.

Step 1: Check Regulations & Plan Materials: None yet — just your design/plan (graph paper or free shed-plan software)

Tools: None

Skills to find: None required, but if your shed is large or near a boundary, a quick chat with your local planning/building department saves headaches later

What to do: Confirm permit requirements, setback distances from boundaries, and max height/size allowed without permission. Sketch your design and finalize dimensions.

Step 2: Prepare the Site Materials: Landscape fabric (weed barrier) Gravel/crushed stone (for drainage base, ~4-6 in depth) Marking spray paint or stakes + string

Tools: Shovel & spade Wheelbarrow Rake Hand tamper or plate compactor Spirit level (4 ft) or laser level Tape measure Builder's square (for squaring corners)

Skills to find: Basic site leveling — not hard, but a laser level rental helps a lot if the ground has any slope If you have poor drainage/heavy clay soil, worth asking a landscaper for advice What to do: Clear vegetation, mark the footprint, excavate and level, add compacted gravel base for drainage.

... """

I won't include the whole document, can share it further but anyone can replicate just by asking sonnet

I just don't understand the need for such hyperbole, and pretending that models are still gpt3, when you can get counter evidence in seconds.

It reminds me of the craze teachers had against trusting Wikipedia - yes, you shouldn't take all claims at face value, but arguing that nothing from Wikipedia could be useful just makes the argument silly.

This feels like an impossible assessment - yes, a model probably can't give you the education that a advanced/expert book on a topic will, but implying that having a verifiable goal is somehow fake learning feels like an intractable problem.

What level of evidence would be sufficient for you to accept that a model may be able to teach a concept?

I'm happy to take on this challenge with a topic of your choosing, but I don't believe there will be an evidence base that satisfies you that the knowledge is earned or deep enough.

This would be a valid point maybe 3 years ago, but most chatbots will now query and verify direct sources, especially in research mode.

This is very simple to validate and verify. You could argue it may find false primary sources.

You can condemn models for a variety of other things, but acting as if this is still reality shows a lack of understanding as to modern model capabilities

This post made me write manual code, there's something about hearing the description of this that makes me worry the bubble is going to come home to roost.

The obvious danger of spending so much on inference and creating ever expanding complexities feels like the height of crypto psychosis

If this harness was achieving major mathematical proofs or creating really consequential work, I think I'd feel differently - but I'm unclear based off of this article what this achieves that a typical harness couldnt

I really love this - fantastic that it's open source too as would love to contribute. Is there an opportunity to add fresh new sites on this?

That's a bit of a false comparison - does this font significantly improve your quality of life comparably to a cheaper/open source font? Is this font really that much better than Jetbrains mono?

Why not pay $10,000 for a font if you are spending 8 hours a day looking at text? Probably because that's a obscene price to pay for a font.

I think the problem is that competition in this area is fierce, so as soon as I see a font like this with such an expensive personal use license - my first thought is - is this really going to be a unique experience compared to the quality of open source fonts?

Yes - fonts arent free - and obviously they're going for a market that will want to spend $250 on a personal font - but if so, I don't think the marketing works for achieving this

I think whenever a blog post begins to sound like a marketing campaign from versace - it's always a great sign that it may be LLM generated.

This isn't just a comment. It's a an experience. A shared cognition between parties -- To collaborate & exchange ideas. It's not procrastination, it's culture. Culture is what builds civilization.

Lifelong windows user here - gave up last year, switched to macos for laptop & ubuntu for desktop - haven't turned back since

Nope, plenty of complex tasks. It's just not that much better, it's equivalent to sonnet with a good harness.

I think the fable it's referring to is the "Emperor has No Clothes" - if this is even slightly similar to the Mythos hyped up to be too intelligent to release, I'm quite disappointed.

If this was a step change, e.g a Opus 5, I'd be pleased, it's definitely an upgrade on some work, but it's nothing like anthropics apocalyptical marketing seemed to suggest

Seduced, shaggy Samson snored.

She scissored short. Sorely shorn,

Soon shackled slave, Samson sighed.

Silently scheming,

Sightlessly seeking

Some savage, spectacular suicide.

- That's the translated Cyberiad Poem the blog post based it off off (or the AI decided to do so)

Doesn't work too well on desktop either! This is decent but it's also an early hackathon set-up - this is something that you can set up on a sonnet model fairly easily (without the weird CSS slop that anthropic models seem to love).

I'm not very threatened by this if this is the dangerous Mythos model - it just seems like a slightly incrementally better sonnet

Not to get too reductive - but LLMs are essentially performing massive number-crunching at a textual representation level. If you've ever played around with early NLP models, they can give you some astounding results for aspects like sentiment analysis that would seem like creative problem solving to someone in 1950. You could say the same for using a neural network to perform things like object recognition.

That's not removing the amazing ability of LLMs and the scale of this accomplishment, don't get me wrong - it's incredibly impressive that specialised models are now able to walk down pathways for creative problem solving - but I don't think that suggests a sentience or profoundness - rather it's just number-crunching at a astronomically larger scale.